Know when to switch
A meter for every chat and every agent: context fill, 5-hour and weekly limits, and the clock time each one resets. Amber, then red, before you hit the wall.
Local-first AI usage tracker
Every AI prompt pays a toll. Token Tollbooth shows the meter.
Watch every agent's usage, get warned before a chat bloats, and hand the work to a fresh agent in one click. It runs on your computer: no accounts, no telemetry.
Free and MIT-licensed. First public release coming soon.
Try the meter
This is one toll booth from the desktop bar, with sample numbers. Push a limit up and the light changes, more windows light up, and at 100% the booth locks: the light turns red, the boom gate drops and the dial goes purple until the reset. Fill the context past 75% and the gate drops too: time to hand off to a fresh chat. The city at the top of the page follows along.
Running tests
ctx 38% · max 46%
LOCKED · until Mon 3 AM
RESETS
Light: Green, all clear.
Why Token Tollbooth
Every time an agent re-reads a bloated Markdown file, you pay for it. Token Tollbooth keeps the work moving and the files lean.
A meter for every chat and every agent: context fill, 5-hour and weekly limits, and the clock time each one resets. Amber, then red, before you hit the wall.
Move a task from one agent to another, from Claude to Codex or Cursor, an app or a terminal, on this computer or another. A handoff is plain text, with the model, mode and speed to use next.
See which sheets your chats keep re-reading and how fast they grow. Condense moves old entries into an archive after you approve a preview. Nothing is deleted, and the next agent reads less.
Handoffs, the logbook and job history are readable text on your own disk, so you always know what was worked on, by which agent, and what happened next.
How it works
Start the dashboard with one Python command, or add the desktop bar on Omarchy. Every chat gets a context gauge, and every tool shows its 5-hour and weekly limits with the time each one resets.
Green, then amber, then red. At 75% full (you choose the line) the gauge flashes START A NEW CHAT, and a limit near its cap turns the light red before you hit the wall.
Press New chat and get a ready-to-paste handoff: the goal, decisions and next step, plus which model, mode and speed to use. Paste it into a fresh chat, in the same agent or another, and keep going.
Hand off between agents
A chat that is too full costs more with every message. Token Tollbooth turns it into a short, reviewed handoff you paste into a fresh chat, in the same agent or a different one.
Project — what it's working on · Speed · model · date, editable, plus Copy chat name for renaming by hand.Token Tollbooth makes no AI call itself. If you ask the current chat to write the summary, that chat spends its own tokens answering. A shorter handoff can carry less context into the new chat, but no specific savings are promised.
Handoff sample
From Claude Code · context 82% full
Subject line
Billing API — Add retries to the invoice sync · High · claude-sonnet-5-5 · Nov 18
Next agent
Claude CodeCodex CLICursorOllama
Set model claude-sonnet-5-5, mode Plan, speed High → paste this handoff
Features
A dashboard that runs anywhere Python does, and a native desktop bar for Omarchy.
LinuxWindows (coming soon)macOS (untested)
127.0.0.1:8937.OmarchyHyprlandQuickshell
Private by design
Token Tollbooth has no server, no account and no telemetry. There is nothing to sign up for, and nothing is sent to us.
The dashboard listens on 127.0.0.1, so only your own computer can open it. Settings and saved handoffs live in a folder next to the app.
To show “Thinking…” or “Running tests”, the desktop bar reads local session files for timestamps, tool names, file names and the first word of commands. Chat text is never read out.
Live feeds are off until you turn them on. The only network requests are the ones that fetch your own usage straight from your AI providers: the bar's percentages through ai-usagebar, and the dashboard's optional API spend report.
MIT-licensed. Read every line before you run it once the repository is public.
Install
The repository is being prepared for its first public release. Until then, here is what getting started will look like.
Needs Python 3.10 or newer. Nothing else to install, no API key.
# preview: available with the first release
git clone https://github.com/TokenTollbooth/tokentollbooth
cd tokentollbooth
python3 token_tollbooth.py
# then open http://127.0.0.1:8937
Starts with clearly labelled sample data. Windows support is coming soon.
The bar lives in the omarchy-plugin/ folder of the same repository. It needs Omarchy (Hyprland and Quickshell), Python 3 and ai-usagebar for the usage numbers.
Step-by-step install instructions arrive with the release.
The code opens on GitHub with the first public release, coming soon. Check back here at tokentollbooth.com: this page will have the download and install steps on launch day.
What's next
Planned, not built yet. Each item moves up to Features when it ships.
FAQ
No, not by default. Token Tollbooth only moves and merges: Condense moves old entries into an archive after you approve a preview, and keeps a dated copy first. The upcoming tidy-up guide works the same way. The only thing it will remove is a file left completely empty after a merge, and only after you confirm that exact file. For developers there is a setting to allow deleting files, and it is off unless you turn it on.
Purple means locked: that allowance, for example your weekly limit, is used up. Nothing is broken. The provider will not take more work on that plan until the window resets, and the badge tells you when, for example LOCKED · until Mon 3 AM. The light turns a steady red and the boom gate comes down, and on the desktop bar the city behind the booth goes into a purple blackout until then. (A blinking red light means a Token Tollbooth alert instead.)
Not to us: there is no server, account or telemetry. Everything is processed on your computer. The only outgoing requests fetch your own usage from your own AI providers (the bar's percentages through ai-usagebar, and the dashboard's optional API spend report, which is off unless you add an admin key).
The desktop bar has booths for Claude (desktop app and Claude Code), Codex (desktop app and CLI), Cursor CLI and Antigravity CLI, plus other providers ai-usagebar knows about. The dashboard has live feeds for Claude Code and Codex CLI, API spend for Anthropic and OpenAI, and can import counters from any tool as JSON.
When a chat gets too full, press New chat (or the handoff button on any gauge or chat card). With live feeds on, Token Tollbooth builds a draft from the local log: your last few messages, the AI's last reply, the folder, the files read and how full the chat was, kept in memory with key-like strings removed. Without live feeds, it gives you a short request to paste into the current chat, and you paste the reply back. Either way you review and edit the goal, decisions, constraints, changed files and next action, it suggests a model, mode and speed for the next agent, and Looks right: save and copy saves it locally and copies it.
Token Tollbooth itself never calls an AI. If you ask the current chat for the summary, that chat spends its own tokens answering. A shorter handoff may carry less context, but no specific savings are guaranteed.
Every message you send re-sends the whole conversation so far. The fuller a chat's context window, the more each prompt costs in tokens and allowance. Token Tollbooth shows how full each chat is and, when it is time, hands you a short summary to paste into a fresh chat.
Linux today. Windows support is being finished and is coming soon. macOS will probably work but is not confirmed yet. The desktop bar is for Omarchy only.
No. Token Tollbooth is an independent project by Waffle Iron Labs and is not affiliated with Anthropic, OpenAI, Anysphere or Google. Product names are used only to say which tools it works with.
Nothing. It is free, MIT-licensed software.